Exploring Active and Passive Team-Based Coordination

As human-robot teamwork becomes increasingly common, a key challenge is to fluidly and intuitively coordinate team members' interactions. In this work, we explore two modalities of human-robot coordination: active, where agents intentionally attempt to understand and influence the plans of human teammates, and passive, where agents simply react to their human teammates' varying behavior. In our Productivity and Wellness Pal (PaWPal) project, we seek to develop an agent that actively elicits a teammate's constraints, preferences, and goals in order to nudge them towards better behavior. Conversely, in our Coordinating Human-Robot Teamwork project, we take a distributed approach to scheduling where agents passively adapt to teammates' plan executions. Our research hypothesis is that human-robot coordination Figure 1: Screenshots from our ESM study, conducted using techniques will lead to more natural and effective PACO on Android (http://www.pacoapp.com/).